Cover Image

Physics-Informed Video Flare Synthesis and Removal Leveraging Motion Independence between Flare and Scene

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Junqiao, Huang, Yuanfei, Huang, Hua
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

DeflareMamba: Hierarchical Vision Mamba for Contextually Consistent Lens Flare Removal
by: Huang, Yihang, et al.
Published: (2025)

Breaking Spatial Uniformity: Prior-Guided Mamba with Radial Serialization for Lens Flare Removal
by: Fu, Zijia, et al.
Published: (2026)

SLCFormer: Spectral-Local Context Transformer with Physics-Grounded Flare Synthesis for Nighttime Flare Removal
by: Zhu, Xiyu, et al.
Published: (2025)

FlareX: A Physics-Informed Dataset for Lens Flare Removal via 2D Synthesis and 3D Rendering
by: Qu, Lishen, et al.
Published: (2025)

Disentangle Nighttime Lens Flares: Self-supervised Generation-based Lens Flare Removal
by: He, Yuwen, et al.
Published: (2025)

Learning to Remove Lens Flare in Event Camera
by: Han, Haiqian, et al.
Published: (2025)

MIPI 2024 Challenge on Nighttime Flare Removal: Methods and Results
by: Dai, Yuekun, et al.
Published: (2024)

LightsOut: Diffusion-based Outpainting for Enhanced Lens Flare Removal
by: Tsai, Shr-Ruei, et al.
Published: (2025)

Semi-LAR: Semi-supervised Contrastive Learning with Linear Attention for Removal of Nighttime Flares
by: Zhu, Xiyu, et al.
Published: (2026)

Harmonizing Light and Darkness: A Symphony of Prior-guided Data Synthesis and Adaptive Focus for Nighttime Flare Removal
by: Qu, Lishen, et al.
Published: (2024)

CAST-LUT: Tokenizer-Guided HSV Look-Up Tables for Purple Flare Removal
by: Wang, Pu, et al.
Published: (2025)

Tackling Ill-posedness of Reversible Image Conversion with Well-posed Invertible Network
by: Huang, Yuanfei, et al.
Published: (2025)

Beyond Image Prior: Embedding Noise Prior into Conditional Denoising Transformer
by: Huang, Yuanfei, et al.
Published: (2024)

MFDNet: Multi-Frequency Deflare Network for Efficient Nighttime Flare Removal
by: Jiang, Yiguo, et al.
Published: (2024)

Difflare: Removing Image Lens Flare with Latent Diffusion Model
by: Zhou, Tianwen, et al.
Published: (2024)

Learning to See Through Flare
by: Peng, Xiaopeng, et al.
Published: (2025)

Video Perception Models for 3D Scene Synthesis
by: Huang, Rui, et al.
Published: (2025)

SMamDiff: Spatial Mamba for Stochastic Human Motion Prediction
by: Fan, Junqiao, et al.
Published: (2025)

Leveraging Contrast Information for Efficient Document Shadow Removal
by: Liu, Yifan, et al.
Published: (2025)

SceneMI: Motion In-betweening for Modeling Human-Scene Interactions
by: Hwang, Inwoo, et al.
Published: (2025)

GN-FR:Generalizable Neural Radiance Fields for Flare Removal
by: Matta, Gopi Raju, et al.
Published: (2024)

SoftShadow: Leveraging Soft Masks for Penumbra-Aware Shadow Removal
by: Wang, Xinrui, et al.
Published: (2024)

Leveraging Text Localization for Scene Text Removal via Text-aware Masked Image Modeling
by: Wang, Zixiao, et al.
Published: (2024)

Bias-Conflict Sample Synthesis and Adversarial Removal Debias Strategy for Temporal Sentence Grounding in Video
by: Qi, Zhaobo, et al.
Published: (2024)

Physics-based Scene Layout Generation from Human Motion
by: Li, Jianan, et al.
Published: (2024)

InterPhys: Physics-aware Human Motion Synthesis in a Dynamic Scene
by: Xing, Chaoyue, et al.
Published: (2026)

DFDNet: Dynamic Frequency-Guided De-Flare Network
by: Xue, Minglong, et al.
Published: (2025)

Uncertainty-Aware Solar Flare Regression
by: Hong, Jinsu, et al.
Published: (2026)

PromptFlare: Prompt-Generalized Defense via Cross-Attention Decoy in Diffusion-Based Inpainting
by: Na, Hohyun, et al.
Published: (2025)

Zero-Shot Personalized Camera Motion Control for Image-to-Video Synthesis
by: Guhan, Pooja, et al.
Published: (2025)

GPT4Motion: Scripting Physical Motions in Text-to-Video Generation via Blender-Oriented GPT Planning
by: Lv, Jiaxi, et al.
Published: (2023)

CineScene: Implicit 3D as Effective Scene Representation for Cinematic Video Generation
by: Huang, Kaiyi, et al.
Published: (2026)

MoVieDrive: Urban Scene Synthesis with Multi-Modal Multi-View Video Diffusion Transformer
by: Wu, Guile, et al.
Published: (2025)

mmPred: Radar-based Human Motion Prediction in the Dark
by: Fan, Junqiao, et al.
Published: (2025)

Synthesizing Physically Plausible Human Motions in 3D Scenes
by: Pan, Liang, et al.
Published: (2023)

Controllable Weather Synthesis and Removal with Video Diffusion Models
by: Lin, Chih-Hao, et al.
Published: (2025)

Human Motion Synthesis in 3D Scenes via Unified Scene Semantic Occupancy
by: Jingyu, Gong, et al.
Published: (2025)

TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization
by: Pan, Liang, et al.
Published: (2025)

Segment Any Motion in Videos
by: Huang, Nan, et al.
Published: (2025)

Toward Real-Time Surgical Scene Segmentation via a Spike-Driven Video Transformer with Spike-Informed Pretraining
by: Zou, Shihao, et al.
Published: (2025)